-
Notifications
You must be signed in to change notification settings - Fork 3.5k
Open
Labels
kind/bugIssues or changes related a bugIssues or changes related a bugtriage/acceptedIndicates an issue or PR is ready to be actively worked on.Indicates an issue or PR is ready to be actively worked on.
Milestone
Description
Is there an existing issue for this?
- I have searched the existing issues
Environment
- Milvus version:2.6.4
- Deployment mode(standalone or cluster): cluster
- MQ type(rocksmq, pulsar or kafka): pulsar
- SDK version(e.g. pymilvus v2.0.0rc2):
- OS(Ubuntu or CentOS): Ubuntu
- CPU/Memory: CPU
- GPU:
- Others:Current Behavior
AiSAQ index type consumes less RAM usage while loading the index than DISKANN, and the query node module is missing the implementation of the RAM usage estimation for that AiSAQ index type.
An exact code PR regarding that issue was requested (#45246).
Expected Behavior
We suggest that the AiSAQ RAM usage estimation calculation should be as follows:
UsedDiskMemoryRatioAisaq = 1024 (contrary to the UsedDiskMemoryRati,o which is 4)
neededMemSize = indexInfo.IndexSize / UsedDiskMemoryRatioAisaq
neededDiskSize = indexInfo.IndexSize
Steps To Reproduce
Milvus Log
No response
Anything else?
No response
Metadata
Metadata
Assignees
Labels
kind/bugIssues or changes related a bugIssues or changes related a bugtriage/acceptedIndicates an issue or PR is ready to be actively worked on.Indicates an issue or PR is ready to be actively worked on.